x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 185 insertions, 0 deletions

diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c
new file mode 100644
index 000000000..ca5d0f51c
--- /dev/null
+++ b/drivers/gpu/host1x/channel.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Tegra host1x Channel
+ *
+ * Copyright (c) 2010-2013, NVIDIA Corporation.
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+
+#include "channel.h"
+#include "dev.h"
+#include "job.h"
+
+/* Constructor for the host1x device list */
+int host1x_channel_list_init(struct host1x_channel_list *chlist,
+			     unsigned int num_channels)
+{
+	chlist->channels = kzalloc_objs(struct host1x_channel, num_channels);
+	if (!chlist->channels)
+		return -ENOMEM;
+
+	chlist->allocated_channels = bitmap_zalloc(num_channels, GFP_KERNEL);
+	if (!chlist->allocated_channels) {
+		kfree(chlist->channels);
+		return -ENOMEM;
+	}
+
+	mutex_init(&chlist->lock);
+
+	return 0;
+}
+
+void host1x_channel_list_free(struct host1x_channel_list *chlist)
+{
+	bitmap_free(chlist->allocated_channels);
+	kfree(chlist->channels);
+}
+
+int host1x_job_submit(struct host1x_job *job)
+{
+	struct host1x *host = dev_get_drvdata(job->channel->dev->parent);
+
+	return host1x_hw_channel_submit(host, job);
+}
+EXPORT_SYMBOL(host1x_job_submit);
+
+struct host1x_channel *host1x_channel_get(struct host1x_channel *channel)
+{
+	kref_get(&channel->refcount);
+
+	return channel;
+}
+EXPORT_SYMBOL(host1x_channel_get);
+
+/**
+ * host1x_channel_get_index() - Attempt to get channel reference by index
+ * @host: Host1x device object
+ * @index: Index of channel
+ *
+ * If channel number @index is currently allocated, increase its refcount
+ * and return a pointer to it. Otherwise, return NULL.
+ */
+struct host1x_channel *host1x_channel_get_index(struct host1x *host,
+						unsigned int index)
+{
+	struct host1x_channel *ch = &host->channel_list.channels[index];
+
+	if (!kref_get_unless_zero(&ch->refcount))
+		return NULL;
+
+	return ch;
+}
+
+void host1x_channel_stop(struct host1x_channel *channel)
+{
+	struct host1x *host = dev_get_drvdata(channel->dev->parent);
+
+	host1x_hw_cdma_stop(host, &channel->cdma);
+}
+EXPORT_SYMBOL(host1x_channel_stop);
+
+/**
+ * host1x_channel_stop_all() - disable CDMA on allocated channels
+ * @host: host1x instance
+ *
+ * Stop CDMA on allocated channels
+ */
+void host1x_channel_stop_all(struct host1x *host)
+{
+	struct host1x_channel_list *chlist = &host->channel_list;
+	int bit;
+
+	mutex_lock(&chlist->lock);
+
+	for_each_set_bit(bit, chlist->allocated_channels, host->info->nb_channels)
+		host1x_channel_stop(&chlist->channels[bit]);
+
+	mutex_unlock(&chlist->lock);
+}
+
+static void release_channel(struct kref *kref)
+{
+	struct host1x_channel *channel =
+		container_of(kref, struct host1x_channel, refcount);
+	struct host1x *host = dev_get_drvdata(channel->dev->parent);
+	struct host1x_channel_list *chlist = &host->channel_list;
+
+	host1x_hw_cdma_stop(host, &channel->cdma);
+	host1x_cdma_deinit(&channel->cdma);
+
+	clear_bit(channel->id, chlist->allocated_channels);
+}
+
+void host1x_channel_put(struct host1x_channel *channel)
+{
+	kref_put(&channel->refcount, release_channel);
+}
+EXPORT_SYMBOL(host1x_channel_put);
+
+static struct host1x_channel *acquire_unused_channel(struct host1x *host)
+{
+	struct host1x_channel_list *chlist = &host->channel_list;
+	unsigned int max_channels = host->info->nb_channels;
+	unsigned int index;
+
+	mutex_lock(&chlist->lock);
+
+	index = find_first_zero_bit(chlist->allocated_channels, max_channels);
+	if (index >= max_channels) {
+		mutex_unlock(&chlist->lock);
+		dev_err(host->dev, "failed to find free channel\n");
+		return NULL;
+	}
+
+	chlist->channels[index].id = index;
+
+	set_bit(index, chlist->allocated_channels);
+
+	mutex_unlock(&chlist->lock);
+
+	return &chlist->channels[index];
+}
+
+/**
+ * host1x_channel_request() - Allocate a channel
+ * @client: Host1x client this channel will be used to send commands to
+ *
+ * Allocates a new host1x channel for @client. May return NULL if CDMA
+ * initialization fails.
+ */
+struct host1x_channel *host1x_channel_request(struct host1x_client *client)
+{
+	struct host1x *host = dev_get_drvdata(client->dev->parent);
+	struct host1x_channel_list *chlist = &host->channel_list;
+	struct host1x_channel *channel;
+	int err;
+
+	channel = acquire_unused_channel(host);
+	if (!channel)
+		return NULL;
+
+	kref_init(&channel->refcount);
+	mutex_init(&channel->submitlock);
+	channel->client = client;
+	channel->dev = client->dev;
+
+	err = host1x_hw_channel_init(host, channel, channel->id);
+	if (err < 0)
+		goto fail;
+
+	err = host1x_cdma_init(&channel->cdma);
+	if (err < 0)
+		goto fail;
+
+	return channel;
+
+fail:
+	clear_bit(channel->id, chlist->allocated_channels);
+
+	dev_err(client->dev, "failed to initialize channel\n");
+
+	return NULL;
+}
+EXPORT_SYMBOL(host1x_channel_request);